Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull kvm fixes from Paolo Bonzini:
"ARM:

   - Fix EL2 Stage-1 MMIO mappings where a random address was used

   - Fix SMCCC function number comparison when the SVE hint is set

  RISC-V:

   - Fix KVM_GET_REG_LIST API for ISA_EXT registers

   - Fix reading ISA_EXT register of a missing extension

   - Fix ISA_EXT register handling in get-reg-list test

   - Fix filtering of AIA registers in get-reg-list test

  x86:

   - Fixes for TSC_AUX virtualization

   - Stop zapping page tables asynchronously, since we don't zap them as
     often as before"

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm:
  KVM: SVM: Do not use user return MSR support for virtualized TSC_AUX
  KVM: SVM: Fix TSC_AUX virtualization setup
  KVM: SVM: INTERCEPT_RDTSCP is never intercepted anyway
  KVM: x86/mmu: Stop zapping invalidated TDP MMU roots asynchronously
  KVM: x86/mmu: Do not filter address spaces in for_each_tdp_mmu_root_yield_safe()
  KVM: x86/mmu: Open code leaf invalidation from mmu_notifier
  KVM: riscv: selftests: Selectively filter-out AIA registers
  KVM: riscv: selftests: Fix ISA_EXT register handling in get-reg-list
  RISC-V: KVM: Fix riscv_vcpu_get_isa_ext_single() for missing extensions
  RISC-V: KVM: Fix KVM_GET_REG_LIST API for ISA_EXT registers
  KVM: selftests: Assert that vasprintf() is successful
  KVM: arm64: nvhe: Ignore SVE hint in SMCCC function ID
  KVM: arm64: Properly return allocated EL2 VA from hyp_alloc_private_va_range()

17 files changed, 164 insertions, 144 deletions

diff --git a/arch/arm64/include/asm/kvm_hyp.h b/arch/arm64/include/asm/kvm_hyp.h
index b7238c72a04c..66efd67ea7e8 100644
--- a/arch/arm64/include/asm/kvm_hyp.h
+++ b/arch/arm64/include/asm/kvm_hyp.h
@@ -118,7 +118,7 @@ void deactivate_traps_vhe_put(struct kvm_vcpu *vcpu);
 
 u64 __guest_enter(struct kvm_vcpu *vcpu);
 
-bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt);
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
 
 #ifdef __KVM_NVHE_HYPERVISOR__
 void __noreturn __hyp_do_panic(struct kvm_cpu_context *host_ctxt, u64 spsr,
diff --git a/arch/arm64/kvm/hyp/include/nvhe/ffa.h b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
index 1becb10ecd80..d9fd5e6c7d3c 100644
--- a/arch/arm64/kvm/hyp/include/nvhe/ffa.h
+++ b/arch/arm64/kvm/hyp/include/nvhe/ffa.h
@@ -12,6 +12,6 @@
 #define FFA_MAX_FUNC_NUM 0x7F
 
 int hyp_ffa_init(void *pages);
-bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt);
+bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id);
 
 #endif /* __KVM_HYP_FFA_H */
diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
index ab4f5d160c58..6e4dba9eadef 100644
--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
+++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
@@ -634,9 +634,8 @@ out_handled:
 	return true;
 }
 
-bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt)
+bool kvm_host_ffa_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 {
-	DECLARE_REG(u64, func_id, host_ctxt, 0);
 	struct arm_smccc_res res;
 
 	/*
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-init.S b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
index 90fade1b032e..1cc06e6797bd 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-init.S
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-init.S
@@ -57,6 +57,7 @@ __do_hyp_init:
 	cmp	x0, #HVC_STUB_HCALL_NR
 	b.lo	__kvm_handle_stub_hvc
 
+	bic	x0, x0, #ARM_SMCCC_CALL_HINTS
 	mov	x3, #KVM_HOST_SMCCC_FUNC(__kvm_hyp_init)
 	cmp	x0, x3
 	b.eq	1f
diff --git a/arch/arm64/kvm/hyp/nvhe/hyp-main.c b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
index 857d9bc04fd4..2385fd03ed87 100644
--- a/arch/arm64/kvm/hyp/nvhe/hyp-main.c
+++ b/arch/arm64/kvm/hyp/nvhe/hyp-main.c
@@ -368,6 +368,7 @@ static void handle_host_hcall(struct kvm_cpu_context *host_ctxt)
 	if (static_branch_unlikely(&kvm_protected_mode_initialized))
 		hcall_min = __KVM_HOST_SMCCC_FUNC___pkvm_prot_finalize;
 
+	id &= ~ARM_SMCCC_CALL_HINTS;
 	id -= KVM_HOST_SMCCC_ID(0);
 
 	if (unlikely(id < hcall_min || id >= ARRAY_SIZE(host_hcall)))
@@ -392,11 +393,14 @@ static void default_host_smc_handler(struct kvm_cpu_context *host_ctxt)
 
 static void handle_host_smc(struct kvm_cpu_context *host_ctxt)
 {
+	DECLARE_REG(u64, func_id, host_ctxt, 0);
 	bool handled;
 
-	handled = kvm_host_psci_handler(host_ctxt);
+	func_id &= ~ARM_SMCCC_CALL_HINTS;
+
+	handled = kvm_host_psci_handler(host_ctxt, func_id);
 	if (!handled)
-		handled = kvm_host_ffa_handler(host_ctxt);
+		handled = kvm_host_ffa_handler(host_ctxt, func_id);
 	if (!handled)
 		default_host_smc_handler(host_ctxt);
 
diff --git a/arch/arm64/kvm/hyp/nvhe/psci-relay.c b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
index 24543d2a3490..d57bcb6ab94d 100644
--- a/arch/arm64/kvm/hyp/nvhe/psci-relay.c
+++ b/arch/arm64/kvm/hyp/nvhe/psci-relay.c
@@ -273,9 +273,8 @@ static unsigned long psci_1_0_handler(u64 func_id, struct kvm_cpu_context *host_
 	}
 }
 
-bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt)
+bool kvm_host_psci_handler(struct kvm_cpu_context *host_ctxt, u32 func_id)
 {
-	DECLARE_REG(u64, func_id, host_ctxt, 0);
 	unsigned long ret;
 
 	switch (kvm_host_psci_config.version) {
diff --git a/arch/arm64/kvm/mmu.c b/arch/arm64/kvm/mmu.c
index 587a104f66c3..482280fe22d7 100644
--- a/arch/arm64/kvm/mmu.c
+++ b/arch/arm64/kvm/mmu.c
@@ -652,6 +652,9 @@ int hyp_alloc_private_va_range(size_t size, unsigned long *haddr)
 
 	mutex_unlock(&kvm_hyp_pgd_mutex);
 
+	if (!ret)
+		*haddr = base;
+
 	return ret;
 }
 
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 1b7e9fa265cb..b7e0e03c69b1 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -460,8 +460,11 @@ static int riscv_vcpu_get_isa_ext_single(struct kvm_vcpu *vcpu,
 	    reg_num >= ARRAY_SIZE(kvm_isa_ext_arr))
 		return -ENOENT;
 
-	*reg_val = 0;
 	host_isa_ext = kvm_isa_ext_arr[reg_num];
+	if (!__riscv_isa_extension_available(NULL, host_isa_ext))
+		return -ENOENT;
+
+	*reg_val = 0;
 	if (__riscv_isa_extension_available(vcpu->arch.isa, host_isa_ext))
 		*reg_val = 1; /* Mark the given extension as available */
 
@@ -842,7 +845,7 @@ static int copy_isa_ext_reg_indices(const struct kvm_vcpu *vcpu,
 		u64 reg = KVM_REG_RISCV | size | KVM_REG_RISCV_ISA_EXT | i;
 
 		isa_ext = kvm_isa_ext_arr[i];
-		if (!__riscv_isa_extension_available(vcpu->arch.isa, isa_ext))
+		if (!__riscv_isa_extension_available(NULL, isa_ext))
 			continue;
 
 		if (uindices) {
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 1a4def36d5bb..17715cb8731d 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1419,7 +1419,6 @@ struct kvm_arch {
 	 * the thread holds the MMU lock in write mode.
 	 */
 	spinlock_t tdp_mmu_pages_lock;
-	struct workqueue_struct *tdp_mmu_zap_wq;
 #endif /* CONFIG_X86_64 */
 
 	/*
@@ -1835,7 +1834,7 @@ void kvm_mmu_vendor_module_exit(void);
 
 void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
 int kvm_mmu_create(struct kvm_vcpu *vcpu);
-int kvm_mmu_init_vm(struct kvm *kvm);
+void kvm_mmu_init_vm(struct kvm *kvm);
 void kvm_mmu_uninit_vm(struct kvm *kvm);
 
 void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index e1d011c67cc6..f7901cb4d2fa 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -6167,20 +6167,15 @@ static bool kvm_has_zapped_obsolete_pages(struct kvm *kvm)
 	return unlikely(!list_empty_careful(&kvm->arch.zapped_obsolete_pages));
 }
 
-int kvm_mmu_init_vm(struct kvm *kvm)
+void kvm_mmu_init_vm(struct kvm *kvm)
 {
-	int r;
-
 	INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
 	INIT_LIST_HEAD(&kvm->arch.zapped_obsolete_pages);
 	INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
 	spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
 
-	if (tdp_mmu_enabled) {
-		r = kvm_mmu_init_tdp_mmu(kvm);
-		if (r < 0)
-			return r;
-	}
+	if (tdp_mmu_enabled)
+		kvm_mmu_init_tdp_mmu(kvm);
 
 	kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
 	kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
@@ -6189,8 +6184,6 @@ int kvm_mmu_init_vm(struct kvm *kvm)
 
 	kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
 	kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
-
-	return 0;
 }
 
 static void mmu_free_vm_memory_caches(struct kvm *kvm)
@@ -6246,7 +6239,6 @@ static bool kvm_rmap_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_e
 void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 {
 	bool flush;
-	int i;
 
 	if (WARN_ON_ONCE(gfn_end <= gfn_start))
 		return;
@@ -6257,11 +6249,8 @@ void kvm_zap_gfn_range(struct kvm *kvm, gfn_t gfn_start, gfn_t gfn_end)
 
 	flush = kvm_rmap_zap_gfn_range(kvm, gfn_start, gfn_end);
 
-	if (tdp_mmu_enabled) {
-		for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
-			flush = kvm_tdp_mmu_zap_leafs(kvm, i, gfn_start,
-						      gfn_end, true, flush);
-	}
+	if (tdp_mmu_enabled)
+		flush = kvm_tdp_mmu_zap_leafs(kvm, gfn_start, gfn_end, flush);
 
 	if (flush)
 		kvm_flush_remote_tlbs_range(kvm, gfn_start, gfn_end - gfn_start);
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index b102014e2c60..decc1f153669 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -58,7 +58,12 @@ struct kvm_mmu_page {
 
 	bool tdp_mmu_page;
 	bool unsync;
-	u8 mmu_valid_gen;
+	union {
+		u8 mmu_valid_gen;
+
+		/* Only accessed under slots_lock.  */
+		bool tdp_mmu_scheduled_root_to_zap;
+	};
 
 	 /*
 	  * The shadow page can't be replaced by an equivalent huge page
@@ -100,13 +105,7 @@ struct kvm_mmu_page {
 		struct kvm_rmap_head parent_ptes; /* rmap pointers to parent sptes */
 		tdp_ptep_t ptep;
 	};
-	union {
-		DECLARE_BITMAP(unsync_child_bitmap, 512);
-		struct {
-			struct work_struct tdp_mmu_async_work;
-			void *tdp_mmu_async_data;
-		};
-	};
+	DECLARE_BITMAP(unsync_child_bitmap, 512);
 
 	/*
 	 * Tracks shadow pages that, if zapped, would allow KVM to create an NX
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 6c63f2d1675f..6cd4dd631a2f 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -12,18 +12,10 @@
 #include <trace/events/kvm.h>
 
 /* Initializes the TDP MMU for the VM, if enabled. */
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm)
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm)
 {
-	struct workqueue_struct *wq;
-
-	wq = alloc_workqueue("kvm", WQ_UNBOUND|WQ_MEM_RECLAIM|WQ_CPU_INTENSIVE, 0);
-	if (!wq)
-		return -ENOMEM;
-
 	INIT_LIST_HEAD(&kvm->arch.tdp_mmu_roots);
 	spin_lock_init(&kvm->arch.tdp_mmu_pages_lock);
-	kvm->arch.tdp_mmu_zap_wq = wq;
-	return 1;
 }
 
 /* Arbitrarily returns true so that this may be used in if statements. */
@@ -46,20 +38,15 @@ void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm)
 	 * ultimately frees all roots.
 	 */
 	kvm_tdp_mmu_invalidate_all_roots(kvm);
-
-	/*
-	 * Destroying a workqueue also first flushes the workqueue, i.e. no
-	 * need to invoke kvm_tdp_mmu_zap_invalidated_roots().
-	 */
-	destroy_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	kvm_tdp_mmu_zap_invalidated_roots(kvm);
 
 	WARN_ON(atomic64_read(&kvm->arch.tdp_mmu_pages));
 	WARN_ON(!list_empty(&kvm->arch.tdp_mmu_roots));
 
 	/*
 	 * Ensure that all the outstanding RCU callbacks to free shadow pages
-	 * can run before the VM is torn down.  Work items on tdp_mmu_zap_wq
-	 * can call kvm_tdp_mmu_put_root and create new callbacks.
+	 * can run before the VM is torn down.  Putting the last reference to
+	 * zapped roots will create new callbacks.
 	 */
 	rcu_barrier();
 }
@@ -86,46 +73,6 @@ static void tdp_mmu_free_sp_rcu_callback(struct rcu_head *head)
 	tdp_mmu_free_sp(sp);
 }
 
-static void tdp_mmu_zap_root(struct kvm *kvm, struct kvm_mmu_page *root,
-			     bool shared);
-
-static void tdp_mmu_zap_root_work(struct work_struct *work)
-{
-	struct kvm_mmu_page *root = container_of(work, struct kvm_mmu_page,
-						 tdp_mmu_async_work);
-	struct kvm *kvm = root->tdp_mmu_async_data;
-
-	read_lock(&kvm->mmu_lock);
-
-	/*
-	 * A TLB flush is not necessary as KVM performs a local TLB flush when
-	 * allocating a new root (see kvm_mmu_load()), and when migrating vCPU
-	 * to a different pCPU.  Note, the local TLB flush on reuse also
-	 * invalidates any paging-structure-cache entries, i.e. TLB entries for
-	 * intermediate paging structures, that may be zapped, as such entries
-	 * are associated with the ASID on both VMX and SVM.
-	 */
-	tdp_mmu_zap_root(kvm, root, true);
-
-	/*
-	 * Drop the refcount using kvm_tdp_mmu_put_root() to test its logic for
-	 * avoiding an infinite loop.  By design, the root is reachable while
-	 * it's being asynchronously zapped, thus a different task can put its
-	 * last reference, i.e. flowing through kvm_tdp_mmu_put_root() for an
-	 * asynchronously zapped root is unavoidable.
-	 */
-	kvm_tdp_mmu_put_root(kvm, root, true);
-
-	read_unlock(&kvm->mmu_lock);
-}
-
-static void tdp_mmu_schedule_zap_root(struct kvm *kvm, struct kvm_mmu_page *root)
-{
-	root->tdp_mmu_async_data = kvm;
-	INIT_WORK(&root->tdp_mmu_async_work, tdp_mmu_zap_root_work);
-	queue_work(kvm->arch.tdp_mmu_zap_wq, &root->tdp_mmu_async_work);
-}
-
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared)
 {
@@ -211,8 +158,12 @@ static struct kvm_mmu_page *tdp_mmu_next_root(struct kvm *kvm,
 #define for_each_valid_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared)	\
 	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, _shared, true)
 
-#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id)			\
-	__for_each_tdp_mmu_root_yield_safe(_kvm, _root, _as_id, false, false)
+#define for_each_tdp_mmu_root_yield_safe(_kvm, _root, _shared)			\
+	for (_root = tdp_mmu_next_root(_kvm, NULL, _shared, false);		\
+	     _root;								\
+	     _root = tdp_mmu_next_root(_kvm, _root, _shared, false))		\
+		if (!kvm_lockdep_assert_mmu_lock_held(_kvm, _shared)) {		\
+		} else
 
 /*
  * Iterate over all TDP MMU roots.  Requires that mmu_lock be held for write,
@@ -292,7 +243,7 @@ hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu)
 	 * by a memslot update or by the destruction of the VM.  Initialize the
 	 * refcount to two; one reference for the vCPU, and one reference for
 	 * the TDP MMU itself, which is held until the root is invalidated and
-	 * is ultimately put by tdp_mmu_zap_root_work().
+	 * is ultimately put by kvm_tdp_mmu_zap_invalidated_roots().
 	 */
 	refcount_set(&root->tdp_mmu_root_count, 2);
 
@@ -877,13 +828,12 @@ static bool tdp_mmu_zap_leafs(struct kvm *kvm, struct kvm_mmu_page *root,
  * true if a TLB flush is needed before releasing the MMU lock, i.e. if one or
  * more SPTEs were zapped since the MMU lock was last acquired.
  */
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
-			   bool can_yield, bool flush)
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush)
 {
 	struct kvm_mmu_page *root;
 
-	for_each_tdp_mmu_root_yield_safe(kvm, root, as_id)
-		flush = tdp_mmu_zap_leafs(kvm, root, start, end, can_yield, flush);
+	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+		flush = tdp_mmu_zap_leafs(kvm, root, start, end, true, flush);
 
 	return flush;
 }
@@ -891,7 +841,6 @@ bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start, gfn_t end,
 void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 {
 	struct kvm_mmu_page *root;
-	int i;
 
 	/*
 	 * Zap all roots, including invalid roots, as all SPTEs must be dropped
@@ -905,10 +854,8 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
 	 * is being destroyed or the userspace VMM has exited.  In both cases,
 	 * KVM_RUN is unreachable, i.e. no vCPUs will ever service the request.
 	 */
-	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
-		for_each_tdp_mmu_root_yield_safe(kvm, root, i)
-			tdp_mmu_zap_root(kvm, root, false);
-	}
+	for_each_tdp_mmu_root_yield_safe(kvm, root, false)
+		tdp_mmu_zap_root(kvm, root, false);
 }
 
 /*
@@ -917,18 +864,47 @@ void kvm_tdp_mmu_zap_all(struct kvm *kvm)
  */
 void kvm_tdp_mmu_zap_invalidated_roots(struct kvm *kvm)
 {
-	flush_workqueue(kvm->arch.tdp_mmu_zap_wq);
+	struct kvm_mmu_page *root;
+
+	read_lock(&kvm->mmu_lock);
+
+	for_each_tdp_mmu_root_yield_safe(kvm, root, true) {
+		if (!root->tdp_mmu_scheduled_root_to_zap)
+			continue;
+
+		root->tdp_mmu_scheduled_root_to_zap = false;
+		KVM_BUG_ON(!root->role.invalid, kvm);
+
+		/*
+		 * A TLB flush is not necessary as KVM performs a local TLB
+		 * flush when allocating a new root (see kvm_mmu_load()), and
+		 * when migrating a vCPU to a different pCPU.  Note, the local
+		 * TLB flush on reuse also invalidates paging-structure-cache
+		 * entries, i.e. TLB entries for intermediate paging structures,
+		 * that may be zapped, as such entries are associated with the
+		 * ASID on both VMX and SVM.
+		 */
+		tdp_mmu_zap_root(kvm, root, true);
+
+		/*
+		 * The referenced needs to be put *after* zapping the root, as
+		 * the root must be reachable by mmu_notifiers while it's being
+		 * zapped
+		 */
+		kvm_tdp_mmu_put_root(kvm, root, true);
+	}
+
+	read_unlock(&kvm->mmu_lock);
 }
 
 /*
  * Mark each TDP MMU root as invalid to prevent vCPUs from reusing a root that
  * is about to be zapped, e.g. in response to a memslots update.  The actual
- * zapping is performed asynchronously.  Using a separate workqueue makes it
- * easy to ensure that the destruction is performed before the "fast zap"
- * completes, without keeping a separate list of invalidated roots; the list is
- * effectively the list of work items in the workqueue.
+ * zapping is done separately so that it happens with mmu_lock with read,
+ * whereas invalidating roots must be done with mmu_lock held for write (unless
+ * the VM is being destroyed).
  *
- * Note, the asynchronous worker is gifted the TDP MMU's reference.
+ * Note, kvm_tdp_mmu_zap_invalidated_roots() is gifted the TDP MMU's reference.
  * See kvm_tdp_mmu_get_vcpu_root_hpa().
  */
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
@@ -953,19 +929,20 @@ void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm)
 	/*
 	 * As above, mmu_lock isn't held when destroying the VM!  There can't
 	 * be other references to @kvm, i.e. nothing else can invalidate roots
-	 * or be consuming roots, but walking the list of roots does need to be
-	 * guarded against roots being deleted by the asynchronous zap worker.
+	 * or get/put references to roots.
 	 */
-	rcu_read_lock();
-
-	list_for_each_entry_rcu(root, &kvm->arch.tdp_mmu_roots, link) {
+	list_for_each_entry(root, &kvm->arch.tdp_mmu_roots, link) {
+		/*
+		 * Note, invalid roots can outlive a memslot update!  Invalid
+		 * roots must be *zapped* before the memslot update completes,
+		 * but a different task can acquire a reference and keep the
+		 * root alive after its been zapped.
+		 */
 		if (!root->role.invalid) {
+			root->tdp_mmu_scheduled_root_to_zap = true;
 			root->role.invalid = true;
-			tdp_mmu_schedule_zap_root(kvm, root);
 		}
 	}
-
-	rcu_read_unlock();
 }
 
 /*
@@ -1146,8 +1123,13 @@ retry:
 bool kvm_tdp_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range,
 				 bool flush)
 {
-	return kvm_tdp_mmu_zap_leafs(kvm, range->slot->as_id, range->start,
-				     range->end, range->may_block, flush);
+	struct kvm_mmu_page *root;
+
+	__for_each_tdp_mmu_root_yield_safe(kvm, root, range->slot->as_id, false, false)
+		flush = tdp_mmu_zap_leafs(kvm, root, range->start, range->end,
+					  range->may_block, flush);
+
+	return flush;
 }
 
 typedef bool (*tdp_handler_t)(struct kvm *kvm, struct tdp_iter *iter,
diff --git a/arch/x86/kvm/mmu/tdp_mmu.h b/arch/x86/kvm/mmu/tdp_mmu.h
index 0a63b1afabd3..733a3aef3a96 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.h
+++ b/arch/x86/kvm/mmu/tdp_mmu.h
@@ -7,7 +7,7 @@
 
 #include "spte.h"
 
-int kvm_mmu_init_tdp_mmu(struct kvm *kvm);
+void kvm_mmu_init_tdp_mmu(struct kvm *kvm);
 void kvm_mmu_uninit_tdp_mmu(struct kvm *kvm);
 
 hpa_t kvm_tdp_mmu_get_vcpu_root_hpa(struct kvm_vcpu *vcpu);
@@ -20,8 +20,7 @@ __must_check static inline bool kvm_tdp_mmu_get_root(struct kvm_mmu_page *root)
 void kvm_tdp_mmu_put_root(struct kvm *kvm, struct kvm_mmu_page *root,
 			  bool shared);
 
-bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, int as_id, gfn_t start,
-				 gfn_t end, bool can_yield, bool flush);
+bool kvm_tdp_mmu_zap_leafs(struct kvm *kvm, gfn_t start, gfn_t end, bool flush);
 bool kvm_tdp_mmu_zap_sp(struct kvm *kvm, struct kvm_mmu_page *sp);
 void kvm_tdp_mmu_zap_all(struct kvm *kvm);
 void kvm_tdp_mmu_invalidate_all_roots(struct kvm *kvm);
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index b9a0a939d59f..4900c078045a 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -2962,6 +2962,32 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
 				    count, in);
 }
 
+static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		bool v_tsc_aux = guest_cpuid_has(vcpu, X86_FEATURE_RDTSCP) ||
+				 guest_cpuid_has(vcpu, X86_FEATURE_RDPID);
+
+		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
+	}
+}
+
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+{
+	struct kvm_vcpu *vcpu = &svm->vcpu;
+	struct kvm_cpuid_entry2 *best;
+
+	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
+	best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
+	if (best)
+		vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
+
+	if (sev_es_guest(svm->vcpu.kvm))
+		sev_es_vcpu_after_set_cpuid(svm);
+}
+
 static void sev_es_init_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -3024,14 +3050,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
 	set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
-	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) &&
-	    (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP) ||
-	     guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDPID))) {
-		set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, 1, 1);
-		if (guest_cpuid_has(&svm->vcpu, X86_FEATURE_RDTSCP))
-			svm_clr_intercept(svm, INTERCEPT_RDTSCP);
-	}
 }
 
 void sev_init_vmcb(struct vcpu_svm *svm)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index f283eb47f6ac..9507df93f410 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -683,6 +683,21 @@ static int svm_hardware_enable(void)
 
 	amd_pmu_enable_virt();
 
+	/*
+	 * If TSC_AUX virtualization is supported, TSC_AUX becomes a swap type
+	 * "B" field (see sev_es_prepare_switch_to_guest()) for SEV-ES guests.
+	 * Since Linux does not change the value of TSC_AUX once set, prime the
+	 * TSC_AUX field now to avoid a RDMSR on every vCPU run.
+	 */
+	if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
+		struct sev_es_save_area *hostsa;
+		u32 msr_hi;
+
+		hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400);
+
+		rdmsr(MSR_TSC_AUX, hostsa->tsc_aux, msr_hi);
+	}
+
 	return 0;
 }
 
@@ -1532,7 +1547,14 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
 	if (tsc_scaling)
 		__svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio);
 
-	if (likely(tsc_aux_uret_slot >= 0))
+	/*
+	 * TSC_AUX is always virtualized for SEV-ES guests when the feature is
+	 * available. The user return MSR support is not required in this case
+	 * because TSC_AUX is restored on #VMEXIT from the host save area
+	 * (which has been initialized in svm_hardware_enable()).
+	 */
+	if (likely(tsc_aux_uret_slot >= 0) &&
+	    (!boot_cpu_has(X86_FEATURE_V_TSC_AUX) || !sev_es_guest(vcpu->kvm)))
 		kvm_set_user_return_msr(tsc_aux_uret_slot, svm->tsc_aux, -1ull);
 
 	svm->guest_state_loaded = true;
@@ -3087,6 +3109,16 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
 		break;
 	case MSR_TSC_AUX:
 		/*
+		 * TSC_AUX is always virtualized for SEV-ES guests when the
+		 * feature is available. The user return MSR support is not
+		 * required in this case because TSC_AUX is restored on #VMEXIT
+		 * from the host save area (which has been initialized in
+		 * svm_hardware_enable()).
+		 */
+		if (boot_cpu_has(X86_FEATURE_V_TSC_AUX) && sev_es_guest(vcpu->kvm))
+			break;
+
+		/*
 		 * TSC_AUX is usually changed only during boot and never read
 		 * directly.  Intercept TSC_AUX instead of exposing it to the
 		 * guest via direct_access_msrs, and switch it via user return.
@@ -4284,7 +4316,6 @@ static bool svm_has_emulated_msr(struct kvm *kvm, u32 index)
 static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_svm *svm = to_svm(vcpu);
-	struct kvm_cpuid_entry2 *best;
 
 	/*
 	 * SVM doesn't provide a way to disable just XSAVES in the guest, KVM
@@ -4328,12 +4359,8 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
 		set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
 				     !!guest_cpuid_has(vcpu, X86_FEATURE_FLUSH_L1D));
 
-	/* For sev guests, the memory encryption bit is not reserved in CR3.  */
-	if (sev_guest(vcpu->kvm)) {
-		best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
-		if (best)
-			vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
-	}
+	if (sev_guest(vcpu->kvm))
+		sev_vcpu_after_set_cpuid(svm);
 
 	init_vmcb_after_set_cpuid(vcpu);
 }
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f41253958357..be67ab7fdd10 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -684,6 +684,7 @@ void __init sev_hardware_setup(void);
 void sev_hardware_unsetup(void);
 int sev_cpu_init(struct svm_cpu_data *sd);
 void sev_init_vmcb(struct vcpu_svm *svm);
+void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
 void sev_free_vcpu(struct kvm_vcpu *vcpu);
 int sev_handle_vmgexit(struct kvm_vcpu *vcpu);
 int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 6c9c81e82e65..9f18b06bbda6 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12308,9 +12308,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	if (ret)
 		goto out;
 
-	ret = kvm_mmu_init_vm(kvm);
-	if (ret)
-		goto out_page_track;
+	kvm_mmu_init_vm(kvm);
 
 	ret = static_call(kvm_x86_vm_init)(kvm);
 	if (ret)
@@ -12355,7 +12353,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 
 out_uninit_mmu:
 	kvm_mmu_uninit_vm(kvm);
-out_page_track:
 	kvm_page_track_cleanup(kvm);
 out:
 	return ret;